mcp-teams-server MCP Server

What does “mcp-teams-server” MCP Server do?

The mcp-teams-server is a Model Context Protocol (MCP) server implementation designed to integrate with Microsoft Teams. It enables AI assistants to interact with Teams by providing capabilities such as reading messages, creating new messages, replying to existing conversations, and mentioning members within Teams channels or chats. By bridging AI workflows and Teams, this server empowers developers to automate and enhance collaboration, streamline communication, and build intelligent assistants that can access and act on Teams data. The server serves as a middleware, exposing Microsoft Teams functionalities as tools, resources, and context, thus making it easier for LLM-based agents and clients to execute and standardize various Teams-related tasks within their workflows.

List of Prompts

No information found in the repository about prompt templates.

List of Resources

No explicit resources documented in the available repository content.

List of Tools

• Read Messages
  Allows the AI client to fetch and read messages from Microsoft Teams channels or chats.
• Create Messages
  Enables the generation and posting of new messages to Teams channels or chats.
• Reply to Messages
  Facilitates replying to specific messages within Teams threads.
• Mention Members
  Lets the AI tag or mention specific users in a message.

Use Cases of this MCP Server

• Automated Team Notifications
  Automatically send important updates and alerts to Teams channels, ensuring timely communication within organizations.
• Meeting Summaries and Follow-ups
  Post AI-generated meeting summaries or action points directly into Teams channels or chats for enhanced productivity.
• Contextual Q&A Bots
  Implement AI bots that can answer questions based on recent channel activity or conversation history.
• Task Management Integration
  Create or update task lists and send reminders to users by mentioning them in Teams.
• Customer Support Automation
  AI can monitor support channels, respond to queries, and escalate issues as needed by posting or replying in real-time.

How to set it up

Windsurf

1. Ensure Node.js and Windsurf are installed on your system.
2. Locate your Windsurf configuration file (e.g., windsurf.json).
3. Add the mcp-teams-server entry in the mcpServers object.
4. Save the configuration file and restart Windsurf.
5. Verify the server connection in the Windsurf UI.

JSON Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"]
    }
  }
}

Securing API Keys Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"],
      "env": {
        "TEAMS_API_KEY": "${TEAMS_API_KEY}"
      },
      "inputs": {
        "apiKey": "${TEAMS_API_KEY}"
      }
    }
  }
}

Claude

1. Install Claude desktop or web client.
2. Open the Claude configuration panel.
3. Add the MCP server configuration under mcpServers.
4. Save and restart the Claude client.
5. Confirm Teams integration appears in your Claude tools.

JSON Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"]
    }
  }
}

Cursor

1. Install Cursor and ensure Node.js is available.
2. Edit cursor.json or equivalent configuration file.
3. Insert the mcp-teams-server configuration snippet in mcpServers.
4. Save changes and restart Cursor.
5. Validate that the MCP server is running and accessible.

JSON Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"]
    }
  }
}

Cline

1. Install Cline and required prerequisites.
2. Open your Cline configuration file.
3. Add the mcp-teams-server entry under mcpServers.
4. Restart Cline to apply changes.
5. Check for Teams MCP server availability in the client.

JSON Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"]
    }
  }
}

Securing API Keys Example:

{
  "mcpServers": {
    "teams-mcp": {
      "command": "npx",
      "args": ["@mcp-teams-server@latest"],
      "env": {
        "TEAMS_API_KEY": "${TEAMS_API_KEY}"
      },
      "inputs": {
        "apiKey": "${TEAMS_API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "teams-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “teams-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the two tables:
The mcp-teams-server offers solid Teams integration and exposes core tools, but lacks documentation on prompt templates and explicit resources. Sampling and roots support are not detailed. Based on coverage and usability, this MCP rates a 7/10.

MCP Score